Yi-Jen Wang

Learn More
This paper proposes Runge-Kutta neural networks (RKNNs) for identification of unknown dynamical systems described by ordinary differential equations (i.e., ordinary differential equation or ODE systems) with high accuracy. These networks are constructed according to the Runge-Kutta approximation method. The main attraction of the RKNNs is that they(More)
Enterovirus type 71 (EV71) 2A protease exhibited strong transcriptional activity in yeast cells. The transcriptional activity of 2A protease was independent of its protease activity. EV71 2A protease retained its transcriptional activity after truncation of 40 amino acids at the N-terminus but lost this activity after truncation of 60 amino acids at the(More)
This article proposes a new second-order learning algorithm for training the multilayer perceptron (MLP) networks. The proposed algorithm is a revised Newton's method. A forward–backward propagation scheme is first proposed for network computation of the Hessian matrix, H, of the output error function of the MLP. A block Hessian matrix, H b , is then(More)
  • 1